Epidemiological studies design: Analytical studies
Analytical studies
Divided into three:
Cohort
Case control
Correlational
An analytical study must be able to establish that exposure preceded disease, determine if risk factor is necessary and/or sufficient, determine if risk factor is a direct or indirect cause, rule out confounding factors and/or eliminate or reduce systematic bias.
Healthy
exposure
disease
Cohort Study
Use two groups of subjects Subjects
selected on basis of exposure status
Exposed
Not
exposed
May be prospective or retrospective
Seeks to determine whether an exposure affects the likelihood that a person will get the disease
Results usually reported as Relative Risk
Relative risk formula Cumulative incidence risk (CIR): Rexpose= a/(a+b) Rnot-exposed= c/(c+d) Baseline risk is the cumulative risk for ”control group” ie. Not exposed in this example
A ratio of percent of exposed individuals who get the disease compared to percent of not-exposed people who get the disease
Case Control Study Use
two groups of subjects Subjects selected on basis of disease status Disease No
Disease
Retrospective
only Seeks to determine whether a person with the disease was more likely exposed to the risk factor than someone without the disease Results usually reported as odds ratios
Calculating an Odds Ratio (CrossProducts Ratio)
A ratio of the probabilities diseased individuals were/were not exposed is compared to the ratio of probabilities that disease-free people were/were not exposed
Correlational studies
A correlational study determines whether or not two variables are correlated.
This means to study whether an increase or decrease in one variable corresponds to an increase or decrease in the other variable.
Outcome from this study shows:
Positive correlation (an increase in one variable leads to an increase in the other and a decrease in one leads to a decrease in the other.)
Negative correlation (Negative correlation is when an increase in one variable leads to a decrease in another and vice versa)
No correlation (Two variables are uncorrelated when a change in one doesn't lead to a change in the other )
Correlational study ď ľ
A correlation coefficient (r) is usually used
ď ľ
r varies between +1 and -1. A value close to +1 indicates a strong positive correlation while a value close to -1 indicates strong negative correlation. A value near zero shows that the variables are uncorrelated.
Coefficient correlation formula
Where: X = variant A Y= variant B
The end